4

42dot

Unified platform for multi-modal urban mobility

Senior Computer Vision Engineer - Autonomous Driving

Computer VisionUpdated on Nov 12
Full-timePangyo-ro, Bundang-gu, Seongnam-si, Gyeonggi-do, South KoreaNo salary listed

About the Job

Requirements

  • A deep understanding of computer vision and deep learning, with at least 2 years of experience researching and developing models.
  • An understanding of 3D geometry, camera models, coordinate transformations, and multi-view geometry, with experience applying these concepts to 3D vision model development.
  • Experience with multi-GPU distributed training and diagnosing and improving training performance, memory usage, and numerical stability.
  • In-depth research or development experience in at least one of multi-task learning, representation learning, or self-supervised learning.

Responsibilities

  • Research and develop unified vision models and learning methods for autonomous driving.
  • Train models across 3D scene understanding tasks, including 3D object detection, road structure understanding, and occupancy prediction, using large-scale driving data, while improving the efficiency and stability of distributed training across multiple GPUs and nodes.
  • Investigate performance regressions observed in real-world driving and evaluation and develop visual representations that generalize across diverse driving environments through representation learning and self-supervised learning.
  • Develop multi-camera and LiDAR-based 3D perception decoders and prediction heads.
  • Develop and enhance perception tasks, including 3D object detection, motion prediction, traffic light detection, lane and road geometry estimation, and occupancy prediction.
  • Research and develop multi-task learning models and training strategies that integrate autonomous driving perception tasks, including 3D object detection, road structure understanding, and occupancy prediction, grounded in multi-view geometry and 3D scene representation.
  • Analyze interactions between tasks and improve data composition, sampling, loss balancing, and training schedules to enhance both individual task performance and overall model performance.
  • Identify and optimize computation, memory, communication, and data pipeline bottlenecks in large-scale multi-GPU and multi-node training.
  • Reproduce performance regressions and failure cases identified through model changes and real-world driving evaluation, and determine their causes through quantitative and qualitative analysis.
  • Formulate hypotheses and conduct ablation studies to distinguish the effects of data and ground-truth quality, preprocessing, model architecture, training conditions, and deployment.
  • Research and develop representation learning and self-supervised learning methods using large-scale unlabeled driving data.
  • Design and validate pre-training recipes combining self-supervision, knowledge distillation, and auxiliary supervision, using multi-view, temporal, and geometric information.
  • Investigate representation collapse and training instability, and evaluate representation quality and transfer to downstream tasks.

Desired Qualifications

  • A record of presenting research at top-tier conferences in computer vision, robotics, or machine learning.
  • Experience improving scaling efficiency and GPU resource utilization in large-scale multi-node training.
  • Experience addressing loss balancing, task interference, negative transfer, or other key challenges in multi-task learning.
  • Experience developing BEV- or PV-based 3D scene representations using multi-camera and temporal information.

About the Company

42dot

Unified platform for multi-modal urban mobility

42dot.ai provides a platform called UMOS (Urban Mobility Operating System) that connects and manages multiple transportation modes—such as cars and drones—within a single system for cities, agencies, and private clients. UMOS enables efficient transportation management, demand-response services, and smart logistics by integrating data and operations across modes, powering operations through a subscription-based platform-as-a-service model. Unlike single-mode solutions, 42dot.ai offers multi-modal, city-focused orchestration that bridges public, private, and logistics needs. The company aims to transform urban mobility by helping cities run more efficiently, cut costs, and improve the experience for commuters and logistics providers.

Company size
501-1,000
Company stage
Growth Equity (Venture Capital)
Total funding
$731.9M
Headquarters
Seoul, South Korea
Founded
2019

Recently Posted Jobs

Explore more opportunities at 42dot

See more jobs